A protective effect of statins on primary liver cancer (PLC) risk has been suggested. However, issues about the dose-response relationship, the protective effect of individual statins, and PLC risk reduction among at-risk populations remain unsolved. Therefore, a meta-analysis was conducted. PubMed and EMBASE were searched for studies providing the risk ratio (RR) on statins and PLC risk. Summary RRs were calculated using a random-effects model. Twenty-five studies were identified. Stain use was significantly associated with a reduced risk of PLC (RR = 0.60, 95% confidence interval (CI) = 0.53-0.69). The summary RR for every additional 50 cumulative defined daily doses per year was 0.87 (95% CI = 0.83-0.91). Evidence of a non-linear dose-response relationship between statins and PLC risk was found (Pnon-linearity < 0.01). All individual statins significantly reduced PLC risk, and the risk reduction was more evident with rosuvastatin. The inverse association between statins and PLC risk remained among populations with common risk factors. Subgroup analyses revealed more significant reduction in PLC risk by statins in high- versus non-high-risk populations (Pinteraction = 0.02). Overall, these findings add to our understanding of the association between statins and PLC risk. Whether statin use is causally associated with a reduced risk of PLC should be further studied.